Loading...
Please wait, while we are loading the content...
Similar Documents
On Learning µ-Perceptron Networks with Binary Weights (1992)
| Content Provider | CiteSeerX |
|---|---|
| Author | Golea, Mostefa Marchand, Mario Hancock, Thomas R. |
| Description | Neural networks with binary weights are very important from both the theoretical and practical points of view. In this paper, we investigate the learnability of single binary perceptrons and unions of -binary-perceptron networks, i.e. an "OR" of binary perceptrons where each input unit is connected to one and only one perceptron. We give a polynomial time algorithm that PAC learns these networks under the uniform distribution. The algorithm is able to identify both the network connectivity and the weight values necessary to represent the target function. These results suggest that, under reasonable distributions, -perceptron networks may be easier to learn than fully connected networks. |
| File Format | |
| Language | English |
| Publisher | Morgan Kaufmann Publishers Inc. |
| Publisher Date | 1992-01-01 |
| Publisher Institution | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS |
| Access Restriction | Open |
| Subject Keyword | Network Connectivity Input Unit Practical Point Binary Perceptrons Reasonable Distribution Neural Network Learning Perceptron Network Target Function Binary Weight Binary-perceptron Network Weight Value Polynomial Time Algorithm Single Binary Perceptrons Uniform Distribution |
| Content Type | Text |
| Resource Type | Article |
